CoolFace
Modelpublic

Sathman/Meditation-Agent-SmolLM3-3B-GGUF

sourceHugging Faceapache-2.0updated 6mo agoView on Hugging Face
0likes115downloads
Model Card

Meditation Agent (SmolLM3 3B) — Contemplative Teaching AI

This is the 3B branch of the Meditation Agent series, built on HuggingFaceTB/SmolLM3-3B-Base and fine-tuned with the A-LoRA V6 recipe for contemplative teaching.

All 9 teachers blended — Osho, Thich Nhat Hanh, Nisargadatta, Krishnamurti, Eckhart Tolle, Alan Watts, Atmananda, Rupert Spira, Pema Chodron. No system prompt required. Question in, teaching out.

50-question eval summary

This 3B branch was run through a raw 50-question eval after GGUF conversion.

  • —Q8_0: completed 50/50 with 0 request failures and is the highest-fidelity public quant
  • —Q5_K_M: completed 50/50 with 0 request failures and is the recommended default public quant
  • —Q3_K_M: completed 50/50 with 0 request failures, but is weaker and more generic than Q5_K_M
  • —overall read: strong stability for a 3B model, but still below the larger Meditation Agent branches in teacher-specific nuance and factual reliability

Final training setup

SettingValue
Base modelHuggingFaceTB/SmolLM3-3B-Base
MethodA-LoRA V6
FormatQuestion + concept arrows in, pure teaching passage out
Data exported24,031 atoms
V6 formatted set17,088 examples after opener cap
Train / eval split16,233 / 855
Adapter recipeQDoRA + rsLoRA, rank 32, alpha 32
Epochs1
Max sequence length1536
Completion-only lossYes
NEFTunealpha 5

Training result

Merged checkpoint: checkpoint-2000

CheckpointEval lossEval token accuracy
5001.75800.5554
10001.68400.5686
15001.63960.5771
20001.63380.5781

Files

FileSizeUse
Meditation_Agent-SmolLM3-3B-Q8_0.gguf3.05 GBHighest fidelity
Meditation_Agent-SmolLM3-3B-Q5_K_M.gguf2.06 GBRecommended default
Meditation_Agent-SmolLM3-3B-Q3_K_M.gguf1.46 GBSmallest, most brittle
Meditation_Agent-SmolLM3-3B-BF16.gguf5.74 GBArchive / conversion source

Individual Teacher 3B Specialists

Each teacher also has their own dedicated 3B model — same SmolLM3-3B base, trained on single-teacher data only. Use these when you want one specific voice rather than the blended multi-teacher model.

Release recommendation

Recommended default: Meditation_Agent-SmolLM3-3B-Q5_K_M.gguf

Use Q8_0 when you want the strongest public 3B quant, Q5_K_M as the balanced default, and Q3_K_M when size matters most. BF16 is the archive and further-conversion source.

Positioning

This is the lightweight 3B Meditation Agent:

  • —much smaller than the 8B/Phi4 branches
  • —capable of direct contemplative answers without prompt scaffolding
  • —best suited for local inference where memory footprint matters

Related Models


ellam sivamayam — Everything is Shiva's expression.

எல்லாம் சிவமயம்